xxxxxxxxxx

xxxxxxxxxx import numpy as npimport pandas as pdfrom sklearn.neighbors import NearestNeighborsfrom aux import *import time​t1 = time.time()df = pd.read_csv('Motor_Vehicle_Collisions_Crashes.csv')df = df.loc[~df['LOCATION'].isna()]df = df.loc[~(df['LOCATION'] == '(0.0, 0.0)')]​df['ZIP CODE'] = df['ZIP CODE'].astype(str).replace('     ','nan').astype(float)​df = haversine_KNN_impute(df, 'ZIP CODE')df = haversine_KNN_impute(df, 'BOROUGH')​df['ZIP CODE'] = df['ZIP CODE'].astype(int)​#Extract the contributing factors and vehicle types.df = extract_contributing_factors(df)df = extract_vehicle_types(df)​t2 = time.time()print(f'Done doing the preprocessing. Time elapsed {t2-t1} seconds.')

/opt/anaconda3/lib/python3.7/site-packages/IPython/core/interactiveshell.py:3156: DtypeWarning: Columns (3) have mixed types.Specify dtype option on import or set low_memory=False.
  interactivity=interactivity, compiler=compiler, result=result)

Done doing the preprocessing. Time elapsed 148.61166620254517 seconds.

xxxxxxxxxx ​

xxxxxxxxxx

xxxxxxxxxx pd.read_csv('contributing_factors.csv',sep=';')['General'].unique()

array(['Unspecified', 'Distraction', 'Poor Driving', 'Other Vehicular',
       'Physical Disability', 'Driver Behavior', 'Physical Surroundings',
       'Substance Abuse', 'Defective Car', 'Electronic Defective',
       'Phone'], dtype=object)

xxxxxxxxxx df['CONTRIBUTING FACTORS (GENERAL)'].unique()

array(['', 'Physical Surroundings', 'Distraction', 'Poor Driving',
       'Other Vehicular, Other Vehicular', 'Driver Behavior',
       'Other Vehicular', 'Substance Abuse', 'Defective Car',
       'Physical Disability', 'Distraction, Poor Driving',
       'Distraction, Distraction', 'Driver Behavior, Driver Behavior',
       'Distraction, Driver Behavior',
       'Physical Surroundings, Poor Driving',
       'Other Vehicular, Poor Driving', 'Poor Driving, Poor Driving',
       'Other Vehicular, Physical Surroundings',
       'Driver Behavior, Other Vehicular',
       'Distraction, Physical Surroundings',
       'Distraction, Other Vehicular',
       'Distraction, Poor Driving, Poor Driving',
       'Physical Surroundings, Physical Surroundings',
       'Poor Driving, Substance Abuse',
       'Other Vehicular, Other Vehicular, Other Vehicular',
       'Driver Behavior, Physical Surroundings',
       'Distraction, Distraction, Poor Driving',
       'Driver Behavior, Poor Driving',
       'Poor Driving, Poor Driving, Poor Driving',
       'Distraction, Distraction, Distraction, Physical Surroundings, Physical Surroundings',
       'Defective Car, Poor Driving',
       'Distraction, Distraction, Distraction',
       'Driver Behavior, Driver Behavior, Driver Behavior',
       'Distraction, Substance Abuse', 'Defective Car, Driver Behavior',
       'Defective Car, Distraction',
       'Defective Car, Other Vehicular, Other Vehicular',
       'Physical Surroundings, Physical Surroundings, Physical Surroundings',
       'Phone', 'Defective Car, Defective Car',
       'Driver Behavior, Substance Abuse',
       'Distraction, Other Vehicular, Other Vehicular, Other Vehicular',
       'Distraction, Distraction, Distraction, Distraction',
       'Electronic Defective',
       'Other Vehicular, Other Vehicular, Other Vehicular, Other Vehicular, Substance Abuse',
       'Defective Car, Defective Car, Poor Driving',
       'Defective Car, Other Vehicular',
       'Other Vehicular, Substance Abuse',
       'Distraction, Distraction, Distraction, Poor Driving',
       'Distraction, Other Vehicular, Other Vehicular',
       'Other Vehicular, Other Vehicular, Poor Driving',
       'Other Vehicular, Other Vehicular, Substance Abuse',
       'Electronic Defective, Electronic Defective',
       'Poor Driving, Substance Abuse, Substance Abuse',
       'Distraction, Physical Surroundings, Physical Surroundings',
       'Physical Surroundings, Physical Surroundings, Poor Driving',
       'Substance Abuse, Substance Abuse, Substance Abuse',
       'Other Vehicular, Physical Surroundings, Poor Driving',
       'Physical Disability, Substance Abuse',
       'Defective Car, Physical Surroundings',
       'Driver Behavior, Other Vehicular, Other Vehicular',
       'Distraction, Distraction, Distraction, Distraction, Distraction',
       'Distraction, Distraction, Other Vehicular',
       'Distraction, Other Vehicular, Poor Driving',
       'Poor Driving, Poor Driving, Poor Driving, Poor Driving, Poor Driving',
       'Physical Disability, Poor Driving',
       'Physical Disability, Physical Surroundings, Physical Surroundings',
       'Distraction, Poor Driving, Poor Driving, Poor Driving',
       'Other Vehicular, Other Vehicular, Physical Surroundings',
       'Electronic Defective, Electronic Defective, Electronic Defective',
       'Distraction, Distraction, Distraction, Physical Surroundings',
       'Other Vehicular, Other Vehicular, Poor Driving, Poor Driving',
       'Driver Behavior, Driver Behavior, Physical Disability',
       'Poor Driving, Poor Driving, Poor Driving, Poor Driving',
       'Substance Abuse, Substance Abuse',
       'Other Vehicular, Other Vehicular, Other Vehicular, Physical Disability',
       'Other Vehicular, Other Vehicular, Other Vehicular, Poor Driving',
       'Driver Behavior, Other Vehicular, Other Vehicular, Other Vehicular',
       'Physical Disability, Poor Driving, Poor Driving',
       'Defective Car, Substance Abuse',
       'Other Vehicular, Physical Surroundings, Physical Surroundings, Physical Surroundings, Poor Driving',
       'Defective Car, Physical Surroundings, Physical Surroundings',
       'Defective Car, Distraction, Poor Driving',
       'Physical Surroundings, Physical Surroundings, Physical Surroundings, Physical Surroundings, Physical Surroundings',
       'Driver Behavior, Poor Driving, Poor Driving',
       'Defective Car, Other Vehicular, Other Vehicular, Other Vehicular',
       'Distraction, Phone',
       'Distraction, Distraction, Physical Surroundings, Physical Surroundings',
       'Driver Behavior, Driver Behavior, Physical Surroundings',
       'Distraction, Distraction, Driver Behavior',
       'Other Vehicular, Other Vehicular, Other Vehicular, Other Vehicular',
       'Physical Surroundings, Substance Abuse',
       'Distraction, Physical Surroundings, Poor Driving',
       'Physical Surroundings, Physical Surroundings, Physical Surroundings, Physical Surroundings',
       'Other Vehicular, Other Vehicular, Other Vehicular, Other Vehicular, Other Vehicular',
       'Distraction, Distraction, Distraction, Other Vehicular',
       'Other Vehicular, Poor Driving, Poor Driving',
       'Electronic Defective, Other Vehicular',
       'Physical Surroundings, Poor Driving, Poor Driving',
       'Driver Behavior, Other Vehicular, Other Vehicular, Other Vehicular, Other Vehicular',
       'Distraction, Other Vehicular, Poor Driving, Poor Driving, Poor Driving',
       'Physical Disability, Physical Surroundings',
       'Driver Behavior, Poor Driving, Poor Driving, Poor Driving',
       'Other Vehicular, Physical Disability',
       'Distraction, Distraction, Distraction, Distraction, Poor Driving',
       'Defective Car, Distraction, Distraction',
       'Distraction, Distraction, Physical Surroundings',
       'Driver Behavior, Driver Behavior, Driver Behavior, Poor Driving, Poor Driving',
       'Distraction, Distraction, Poor Driving, Poor Driving',
       'Distraction, Poor Driving, Poor Driving, Poor Driving, Poor Driving',
       'Driver Behavior, Other Vehicular, Poor Driving',
       'Distraction, Driver Behavior, Other Vehicular, Other Vehicular',
       'Driver Behavior, Physical Disability',
       'Other Vehicular, Other Vehicular, Phone',
       'Distraction, Other Vehicular, Physical Surroundings',
       'Driver Behavior, Physical Surroundings, Physical Surroundings',
       'Other Vehicular, Other Vehicular, Other Vehicular, Other Vehicular, Poor Driving',
       'Other Vehicular, Other Vehicular, Physical Disability',
       'Driver Behavior, Other Vehicular, Other Vehicular, Other Vehicular, Poor Driving',
       'Distraction, Other Vehicular, Other Vehicular, Other Vehicular, Other Vehicular',
       'Distraction, Driver Behavior, Poor Driving',
       'Electronic Defective, Poor Driving, Poor Driving',
       'Driver Behavior, Driver Behavior, Driver Behavior, Driver Behavior',
       'Driver Behavior, Other Vehicular, Physical Surroundings',
       'Distraction, Other Vehicular, Poor Driving, Poor Driving',
       'Defective Car, Poor Driving, Poor Driving',
       'Defective Car, Other Vehicular, Other Vehicular, Other Vehicular, Other Vehicular',
       'Driver Behavior, Driver Behavior, Poor Driving, Poor Driving',
       'Distraction, Driver Behavior, Driver Behavior, Driver Behavior',
       'Phone, Poor Driving', 'Driver Behavior, Phone',
       'Electronic Defective, Poor Driving',
       'Other Vehicular, Other Vehicular, Other Vehicular, Substance Abuse',
       'Electronic Defective, Physical Surroundings',
       'Distraction, Distraction, Poor Driving, Poor Driving, Poor Driving',
       'Distraction, Electronic Defective',
       'Driver Behavior, Physical Surroundings, Poor Driving',
       'Distraction, Distraction, Electronic Defective',
       'Distraction, Other Vehicular, Other Vehicular, Poor Driving',
       'Physical Disability, Physical Disability',
       'Distraction, Driver Behavior, Driver Behavior',
       'Distraction, Distraction, Physical Surroundings, Poor Driving',
       'Electronic Defective, Other Vehicular, Other Vehicular',
       'Driver Behavior, Driver Behavior, Poor Driving',
       'Substance Abuse, Substance Abuse, Substance Abuse, Substance Abuse',
       'Distraction, Physical Disability',
       'Other Vehicular, Physical Surroundings, Physical Surroundings',
       'Distraction, Physical Surroundings, Physical Surroundings, Physical Surroundings, Physical Surroundings',
       'Phone, Physical Surroundings', 'Other Vehicular, Phone',
       'Driver Behavior, Poor Driving, Poor Driving, Poor Driving, Poor Driving',
       'Physical Surroundings, Physical Surroundings, Substance Abuse',
       'Distraction, Distraction, Driver Behavior, Poor Driving, Poor Driving',
       'Distraction, Other Vehicular, Substance Abuse',
       'Defective Car, Distraction, Distraction, Other Vehicular',
       'Distraction, Driver Behavior, Poor Driving, Poor Driving, Poor Driving',
       'Defective Car, Other Vehicular, Physical Surroundings',
       'Defective Car, Distraction, Other Vehicular',
       'Defective Car, Physical Disability',
       'Other Vehicular, Other Vehicular, Other Vehicular, Other Vehicular, Physical Disability',
       'Driver Behavior, Driver Behavior, Other Vehicular, Other Vehicular, Other Vehicular',
       'Distraction, Driver Behavior, Physical Surroundings, Physical Surroundings, Poor Driving',
       'Distraction, Distraction, Other Vehicular, Physical Surroundings',
       'Distraction, Distraction, Distraction, Poor Driving, Poor Driving',
       'Distraction, Distraction, Distraction, Distraction, Physical Surroundings',
       'Distraction, Driver Behavior, Physical Surroundings',
       'Driver Behavior, Driver Behavior, Other Vehicular',
       'Other Vehicular, Other Vehicular, Other Vehicular, Other Vehicular, Physical Surroundings',
       'Distraction, Distraction, Substance Abuse',
       'Other Vehicular, Poor Driving, Poor Driving, Poor Driving',
       'Defective Car, Phone',
       'Defective Car, Substance Abuse, Substance Abuse',
       'Driver Behavior, Electronic Defective',
       'Distraction, Physical Surroundings, Physical Surroundings, Physical Surroundings',
       'Distraction, Driver Behavior, Physical Disability',
       'Distraction, Distraction, Other Vehicular, Other Vehicular',
       'Defective Car, Distraction, Distraction, Distraction',
       'Other Vehicular, Other Vehicular, Poor Driving, Poor Driving, Poor Driving',
       'Driver Behavior, Physical Surroundings, Physical Surroundings, Physical Surroundings, Physical Surroundings',
       'Defective Car, Physical Surroundings, Poor Driving',
       'Other Vehicular, Other Vehicular, Other Vehicular, Physical Surroundings',
       'Distraction, Distraction, Distraction, Distraction, Driver Behavior',
       'Physical Surroundings, Poor Driving, Poor Driving, Poor Driving',
       'Distraction, Driver Behavior, Other Vehicular, Poor Driving',
       'Defective Car, Other Vehicular, Poor Driving',
       'Driver Behavior, Other Vehicular, Substance Abuse',
       'Poor Driving, Poor Driving, Substance Abuse',
       'Distraction, Poor Driving, Substance Abuse',
       'Distraction, Driver Behavior, Other Vehicular',
       'Other Vehicular, Physical Surroundings, Physical Surroundings, Physical Surroundings, Physical Surroundings',
       'Electronic Defective, Substance Abuse',
       'Distraction, Distraction, Distraction, Driver Behavior',
       'Defective Car, Distraction, Distraction, Distraction, Distraction',
       'Defective Car, Other Vehicular, Other Vehicular, Physical Surroundings',
       'Physical Surroundings, Physical Surroundings, Physical Surroundings, Poor Driving',
       'Defective Car, Physical Surroundings, Physical Surroundings, Physical Surroundings, Physical Surroundings',
       'Physical Surroundings, Poor Driving, Poor Driving, Poor Driving, Poor Driving',
       'Substance Abuse, Substance Abuse, Substance Abuse, Substance Abuse, Substance Abuse',
       'Driver Behavior, Poor Driving, Substance Abuse',
       'Defective Car, Defective Car, Distraction',
       'Driver Behavior, Driver Behavior, Substance Abuse',
       'Other Vehicular, Physical Surroundings, Physical Surroundings, Physical Surroundings',
       'Driver Behavior, Driver Behavior, Driver Behavior, Substance Abuse',
       'Other Vehicular, Physical Disability, Substance Abuse',
       'Defective Car, Physical Surroundings, Physical Surroundings, Poor Driving',
       'Other Vehicular, Substance Abuse, Substance Abuse',
       'Phone, Poor Driving, Poor Driving, Poor Driving, Poor Driving',
       'Distraction, Distraction, Physical Disability',
       'Driver Behavior, Driver Behavior, Other Vehicular, Other Vehicular',
       'Driver Behavior, Driver Behavior, Driver Behavior, Driver Behavior, Driver Behavior',
       'Poor Driving, Poor Driving, Poor Driving, Substance Abuse',
       'Defective Car, Electronic Defective',
       'Driver Behavior, Driver Behavior, Poor Driving, Poor Driving, Poor Driving',
       'Distraction, Other Vehicular, Phone',
       'Defective Car, Defective Car, Defective Car',
       'Defective Car, Defective Car, Other Vehicular',
       'Driver Behavior, Driver Behavior, Driver Behavior, Poor Driving',
       'Phone, Phone',
       'Physical Disability, Physical Disability, Physical Disability, Physical Disability, Physical Disability',
       'Distraction, Other Vehicular, Physical Disability',
       'Electronic Defective, Electronic Defective, Electronic Defective, Electronic Defective',
       'Distraction, Physical Disability, Physical Disability',
       'Other Vehicular, Other Vehicular, Physical Surroundings, Physical Surroundings',
       'Distraction, Physical Disability, Poor Driving',
       'Distraction, Physical Disability, Physical Disability, Physical Disability',
       'Physical Disability, Physical Disability, Physical Disability',
       'Physical Disability, Physical Disability, Physical Disability, Physical Disability',
       'Electronic Defective, Physical Disability', 'Phone, Phone, Phone',
       'Driver Behavior, Physical Surroundings, Physical Surroundings, Physical Surroundings',
       'Driver Behavior, Substance Abuse, Substance Abuse',
       'Defective Car, Electronic Defective, Electronic Defective',
       'Other Vehicular, Other Vehicular, Other Vehicular, Physical Surroundings, Physical Surroundings',
       'Distraction, Other Vehicular, Other Vehicular, Physical Disability, Physical Disability',
       'Driver Behavior, Physical Disability, Physical Disability',
       'Physical Disability, Physical Surroundings, Physical Surroundings, Physical Surroundings',
       'Other Vehicular, Physical Disability, Physical Disability',
       'Electronic Defective, Physical Disability, Physical Disability',
       'Distraction, Distraction, Driver Behavior, Driver Behavior',
       'Physical Disability, Physical Disability, Poor Driving',
       'Distraction, Distraction, Physical Disability, Physical Disability',
       'Driver Behavior, Driver Behavior, Physical Disability, Physical Disability',
       'Electronic Defective, Physical Disability, Physical Disability, Physical Disability, Poor Driving',
       'Distraction, Physical Disability, Physical Surroundings',
       'Physical Disability, Physical Surroundings, Poor Driving',
       'Physical Disability, Physical Disability, Physical Surroundings',
       'Driver Behavior, Other Vehicular, Physical Disability',
       'Other Vehicular, Other Vehicular, Substance Abuse, Substance Abuse',
       'Driver Behavior, Other Vehicular, Physical Surroundings, Physical Surroundings',
       'Other Vehicular, Physical Disability, Poor Driving',
       'Distraction, Other Vehicular, Other Vehicular, Other Vehicular, Physical Disability',
       'Distraction, Distraction, Distraction, Physical Disability',
       'Defective Car, Defective Car, Defective Car, Defective Car',
       'Physical Disability, Physical Disability, Poor Driving, Poor Driving',
       'Phone, Substance Abuse',
       'Driver Behavior, Electronic Defective, Poor Driving',
       'Phone, Physical Disability',
       'Defective Car, Defective Car, Other Vehicular, Other Vehicular',
       'Physical Surroundings, Physical Surroundings, Physical Surroundings, Substance Abuse',
       'Physical Disability, Physical Disability, Physical Disability, Physical Surroundings',
       'Driver Behavior, Other Vehicular, Other Vehicular, Poor Driving',
       'Electronic Defective, Electronic Defective, Physical Disability',
       'Poor Driving, Poor Driving, Substance Abuse, Substance Abuse, Substance Abuse',
       'Defective Car, Driver Behavior, Poor Driving',
       'Distraction, Physical Disability, Substance Abuse',
       'Physical Disability, Physical Disability, Substance Abuse',
       'Other Vehicular, Physical Disability, Physical Surroundings',
       'Physical Disability, Substance Abuse, Substance Abuse',
       'Distraction, Physical Disability, Physical Disability, Physical Disability, Physical Disability',
       'Other Vehicular, Substance Abuse, Substance Abuse, Substance Abuse',
       'Other Vehicular, Poor Driving, Substance Abuse',
       'Defective Car, Defective Car, Defective Car, Defective Car, Defective Car',
       'Distraction, Other Vehicular, Other Vehicular, Physical Disability',
       'Other Vehicular, Physical Disability, Physical Disability, Physical Disability',
       'Physical Disability, Physical Disability, Physical Disability, Poor Driving',
       'Driver Behavior, Physical Disability, Poor Driving',
       'Distraction, Substance Abuse, Substance Abuse',
       'Other Vehicular, Other Vehicular, Physical Disability, Physical Disability',
       'Distraction, Physical Disability, Physical Disability, Poor Driving',
       'Phone, Poor Driving, Poor Driving',
       'Distraction, Electronic Defective, Electronic Defective',
       'Driver Behavior, Electronic Defective, Electronic Defective',
       'Driver Behavior, Physical Disability, Physical Surroundings',
       'Electronic Defective, Other Vehicular, Physical Disability',
       'Other Vehicular, Physical Disability, Physical Disability, Physical Disability, Physical Disability',
       'Defective Car, Driver Behavior, Electronic Defective',
       'Physical Disability, Physical Disability, Physical Disability, Poor Driving, Poor Driving',
       'Physical Disability, Poor Driving, Poor Driving, Poor Driving',
       'Other Vehicular, Other Vehicular, Other Vehicular, Physical Disability, Physical Disability',
       'Electronic Defective, Physical Disability, Poor Driving',
       'Distraction, Distraction, Distraction, Distraction, Other Vehicular',
       'Distraction, Distraction, Other Vehicular, Other Vehicular, Other Vehicular',
       'Defective Car, Physical Disability, Physical Disability',
       'Driver Behavior, Other Vehicular, Other Vehicular, Physical Disability',
       'Distraction, Other Vehicular, Physical Disability, Physical Disability',
       'Driver Behavior, Physical Disability, Physical Disability, Physical Disability',
       'Other Vehicular, Other Vehicular, Poor Driving, Substance Abuse',
       'Distraction, Driver Behavior, Other Vehicular, Other Vehicular, Other Vehicular',
       'Electronic Defective, Electronic Defective, Other Vehicular',
       'Physical Disability, Physical Disability, Poor Driving, Poor Driving, Substance Abuse',
       'Other Vehicular, Other Vehicular, Physical Disability, Poor Driving',
       'Driver Behavior, Electronic Defective, Substance Abuse',
       'Distraction, Distraction, Other Vehicular, Other Vehicular, Physical Disability',
       'Distraction, Distraction, Distraction, Electronic Defective',
       'Distraction, Electronic Defective, Other Vehicular',
       'Electronic Defective, Electronic Defective, Electronic Defective, Poor Driving',
       'Electronic Defective, Phone',
       'Other Vehicular, Other Vehicular, Physical Disability, Physical Disability, Poor Driving',
       'Defective Car, Poor Driving, Poor Driving, Poor Driving',
       'Distraction, Driver Behavior, Physical Disability, Physical Disability, Physical Disability',
       'Driver Behavior, Physical Disability, Physical Disability, Substance Abuse',
       'Physical Disability, Physical Disability, Substance Abuse, Substance Abuse',
       'Distraction, Electronic Defective, Poor Driving',
       'Distraction, Electronic Defective, Physical Disability',
       'Electronic Defective, Electronic Defective, Poor Driving',
       'Distraction, Other Vehicular, Physical Disability, Poor Driving',
       'Distraction, Electronic Defective, Physical Disability, Physical Disability',
       'Distraction, Electronic Defective, Physical Surroundings',
       'Distraction, Distraction, Physical Disability, Poor Driving',
       'Other Vehicular, Physical Disability, Poor Driving, Poor Driving',
       'Driver Behavior, Driver Behavior, Driver Behavior, Other Vehicular',
       'Electronic Defective, Electronic Defective, Other Vehicular, Other Vehicular',
       'Other Vehicular, Physical Disability, Physical Disability, Physical Disability, Poor Driving',
       'Defective Car, Driver Behavior, Physical Disability',
       'Defective Car, Defective Car, Substance Abuse, Substance Abuse',
       'Physical Surroundings, Physical Surroundings, Poor Driving, Poor Driving',
       'Defective Car, Distraction, Poor Driving, Poor Driving',
       'Distraction, Distraction, Physical Disability, Physical Disability, Physical Disability',
       'Physical Disability, Physical Disability, Physical Disability, Physical Surroundings, Substance Abuse',
       'Driver Behavior, Physical Disability, Substance Abuse',
       'Distraction, Driver Behavior, Substance Abuse',
       'Distraction, Distraction, Distraction, Distraction, Physical Disability',
       'Electronic Defective, Physical Disability, Physical Disability, Physical Disability',
       'Driver Behavior, Driver Behavior, Physical Disability, Substance Abuse',
       'Defective Car, Distraction, Driver Behavior',
       'Electronic Defective, Electronic Defective, Electronic Defective, Electronic Defective, Electronic Defective',
       'Distraction, Other Vehicular, Physical Disability, Physical Disability, Physical Disability',
       'Defective Car, Driver Behavior, Physical Disability, Physical Disability, Poor Driving',
       'Defective Car, Other Vehicular, Physical Disability',
       'Distraction, Distraction, Distraction, Other Vehicular, Other Vehicular',
       'Physical Disability, Poor Driving, Substance Abuse'], dtype=object)

xxxxxxxxxx import matplotlib.pyplot as pltv, c = df.groupby(df['CONTRIBUTING FACTORS (SPECIFIC)']).size().index, df.groupby(df['CONTRIBUTING FACTORS (SPECIFIC)']).size().values plt.style.use('seaborn')plt.figure(figsize=(10, 10))plt.barh(v[(-c).argsort()][1:4], c[(-c).argsort()][1:4])ax = plt.gca()ax.invert_yaxis()plt.title('Contributing Factors', fontsize=25)ax.tick_params(axis='both', which='major', labelsize=25)plt.show()

xxxxxxxxxx

xxxxxxxxxx import matplotlib.pyplot as pltplt.figure(figsize=(20,10))plt.bar(list(df.groupby('BOROUGH').size().index), df.groupby('BOROUGH').size().values)plt.title('Number of collisions for each borough (district)', fontsize=15)

Text(0.5, 1.0, 'Number of collisions for each borough (district)')

xxxxxxxxxx import foliumfrom folium.plugins import HeatMap​#coords = df.loc[df['Category'] == 'SEX OFFENSES, NON FORCIBLE']['location']\#            .apply(lambda x : [float(y) for y in x.replace('POINT (','').replace(')','').split(' ')])\#            .values.tolist()​lat, lon = df[['LATITUDE', 'LONGITUDE']].mean(axis=0)ny_map = folium.Map([lat, lon],                    zoom_start = 11.75,                    tiles = "Stamen Toner")​coords = df[['LATITUDE', 'LONGITUDE']].iloc[:500,:].values.tolist()# Plot it on the map​#From the documentation:#radius (int, default 25) – Radius of each “point” of the heatmap#max_zoom (default 18) – Zoom level where the points reach maximum intensity (as intensity scales with zoom), equals maxZoom of the map by default​HeatMap(coords,radius=15).add_to(ny_map)​#The center of the heatmaps draw a lot of attention. Outliers are harder to spot.#That being said, when points are stacked, it's hard to see exactly how many there are. ny_map

xxxxxxxxxx

xxxxxxxxxx df['CRASH TIMESTAMP'] = pd.to_datetime(df['CRASH DATE'] + ' ' + df['CRASH TIME'], format='%m/%d/%Y %H:%M')

xxxxxxxxxx plt.figure(figsize=(20,10))plt.bar(df.groupby(df['CRASH TIMESTAMP'].dt.weekday).size().index, df.groupby(df['CRASH TIMESTAMP'].dt.weekday).size().values)plt.xticks(range(0,7), ['Monday','Tuesday','Wednesday','Thursday','Friday', 'Satuday', 'Sunday'], fontsize=10)plt.title('Time of Day', fontsize=15)plt.show()

xxxxxxxxxx plt.figure(figsize=(20,10))plt.bar(df.groupby(df['CRASH TIMESTAMP'].dt.month).size().index, df.groupby(df['CRASH TIMESTAMP'].dt.month).size().values)plt.xticks(range(1,13), ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec'])plt.title('Collisions per month', fontsize=15)plt.show()

xxxxxxxxxx plt.figure(figsize=(20,10))plt.bar(df.groupby(df['CRASH TIMESTAMP'].dt.year).size().index, df.groupby(df['CRASH TIMESTAMP'].dt.year).size().values)plt.xticks(range(2012, 2022))plt.title('Collisions per year', fontsize=15)plt.show()

xxxxxxxxxx plt.figure(figsize=(20,10))plt.bar(df.groupby(df['CRASH TIMESTAMP'].dt.hour).size().index, df.groupby(df['CRASH TIMESTAMP'].dt.hour).size().values)plt.xticks(range(0, 24), range(0, 24))ax = plt.gca()ax.tick_params(axis='both', which='major', labelsize=20)plt.title('Collisions per hour', fontsize=30)plt.show()

xxxxxxxxxx

xxxxxxxxxx #Baseline distribution.query_factors = ['right-of-way']df_query = df.loc[[any(y in x for y in query_factors) for x in df['CONTRIBUTING FACTORS']]]​​baseline = df.groupby(df['CRASH TIMESTAMP'].dt.hour).size() / len(df)query = df_query.groupby(df['CRASH TIMESTAMP'].dt.hour).size() / len(df_query)​plt.figure(figsize=(20,10))plt.bar(range(0,24), query/baseline)plt.xticks(range(0,24), range(0,24))plt.axhline(1, c='r', ls='--')plt.show()

xxxxxxxxxx

xxxxxxxxxx plt.figure(figsize=(20,10))plt.scatter(df['CRASH TIMESTAMP'].dt.minute, np.random.randn(len(df))+np.ones(len(df)), alpha=.005)plt.xticks(np.arange(0, 60, 1), [str(x).zfill(2) for x in np.arange(0, 60, 1)])plt.yticks([])plt.show()

xxxxxxxxxx

xxxxxxxxxx

xxxxxxxxxx df_serious = df.loc[(df['NUMBER OF PERSONS INJURED'] + df['NUMBER OF PERSONS KILLED']) > 0]df_lethal = df.loc[df['NUMBER OF PERSONS KILLED'] > 0]

xxxxxxxxxx plt.figure(figsize=(20,10))plt.bar(range(0, 24), df_serious.groupby(df_serious['CRASH TIMESTAMP'].dt.hour).size() / df.groupby(df['CRASH TIMESTAMP'].dt.hour).size())plt.xlabel('Hour', fontsize=15)plt.ylabel('Risk of being serious', fontsize=15)plt.xticks(range(0,24))plt.show()

xxxxxxxxxx plt.figure(figsize=(20,10))plt.bar(range(0, 24), df_lethal.groupby(df_lethal['CRASH TIMESTAMP'].dt.hour).size() / df.groupby(df['CRASH TIMESTAMP'].dt.hour).size())plt.xlabel('Hour', fontsize=15)plt.ylabel('Risk of being lethal', fontsize=15)plt.xticks(range(0,24))plt.show()

xxxxxxxxxx df_lethal['CRASH TIMESTAMP'].dt.weekday

667        1
805        2
1165       3
1706       4
1891       1
          ..
1762123    0
1763645    6
1763755    2
1765238    1
1765547    3
Name: CRASH TIMESTAMP, Length: 1851, dtype: int64

xxxxxxxxxx

xxxxxxxxxx plt.figure(figsize=(20,10))plt.bar(range(0,24*7), df_serious.groupby([df_serious['CRASH TIMESTAMP'].dt.weekday, df_serious['CRASH TIMESTAMP'].dt.hour]).size()                                 .unstack().fillna(0).values.reshape(-1,))plt.xlim(0, 24*7)plt.show()

xxxxxxxxxx

xxxxxxxxxx injury_columns = [x for x in df.columns if x.startswith('NUMBER OF ')]​for injury in injury_columns:    print(injury.title())    n, nocc = df.groupby(injury).size().index, df.groupby(injury).size().values    for i, j in zip(n, nocc/nocc.sum()):        print(f'{int(i)}, {j}')    print('')

Number Of Persons Injured
0, 0.7976347342723777
1, 0.15766959812722478
2, 0.02901464616144073
3, 0.009548993871829054
4, 0.0036027268882338347
5, 0.0014153799478841935
6, 0.0005772076263396938
7, 0.0002577508442786383
8, 0.00011119924204539758
9, 5.334992537438149e-05
10, 4.0494521669711256e-05
11, 2.1211416112705894e-05
12, 1.60692546308378e-05
13, 1.0284322963736192e-05
14, 3.21385092616756e-06
15, 4.499391296634584e-06
16, 4.499391296634584e-06
17, 2.571080740934048e-06
18, 2.571080740934048e-06
19, 1.928310555700536e-06
20, 1.285540370467024e-06
22, 1.928310555700536e-06
24, 1.928310555700536e-06
27, 6.42770185233512e-07
32, 6.42770185233512e-07
43, 6.42770185233512e-07

Number Of Persons Killed
0, 0.9988102232100962
1, 0.0011531386067463107
2, 2.8282106297010966e-05
3, 5.142201144911085e-06
4, 1.9283254293416567e-06
5, 6.427751431138856e-07
8, 6.427751431138856e-07

Number Of Pedestrians Injured
0, 0.9482208947011856
1, 0.04991509093176293
2, 0.0016409754065800993
3, 0.00017354616520823612
4, 2.8281597293194033e-05
5, 1.0284217197525104e-05
6, 5.784872173607871e-06
7, 1.9282907245359568e-06
9, 1.285527149690638e-06
13, 6.42763574845319e-07
15, 6.42763574845319e-07
27, 6.42763574845319e-07

Number Of Pedestrians Killed
0, 0.9993450239172326
1, 0.0006491912105937722
2, 5.142108598762552e-06
6, 6.42763574845319e-07

Number Of Cyclist Injured
0, 0.9762897372511059
1, 0.023490437606297026
2, 0.0002133975068486459
3, 5.784872173607871e-06
4, 6.42763574845319e-07

Number Of Cyclist Killed
0, 0.9999074420452223
1, 9.191519120288061e-05
2, 6.42763574845319e-07

Number Of Motorist Injured
0, 0.872163323653314
1, 0.0859908393335313
2, 0.026602056072123216
3, 0.009255795477772593
4, 0.0035223443901523477
5, 0.0013941541938394969
6, 0.0005585615465405822
7, 0.00024232186771668525
8, 0.0001086270441488589
9, 5.270661313731615e-05
10, 3.8565814490719133e-05
11, 2.1211197969895526e-05
12, 1.5426325796287654e-05
13, 1.0284217197525104e-05
14, 3.8565814490719135e-06
15, 3.2138178742265947e-06
16, 3.8565814490719135e-06
17, 2.571054299381276e-06
18, 2.571054299381276e-06
19, 1.285527149690638e-06
20, 1.285527149690638e-06
21, 6.42763574845319e-07
22, 1.285527149690638e-06
24, 1.9282907245359568e-06
30, 6.42763574845319e-07
43, 6.42763574845319e-07

Number Of Motorist Killed
0, 0.9995564931333567
1, 0.0004139397422003854
2, 2.2496725119586164e-05
3, 5.142108598762552e-06
4, 1.285527149690638e-06
5, 6.42763574845319e-07

xxxxxxxxxx

xxxxxxxxxx

xxxxxxxxxx plt.figure(figsize=(20,10))plt.scatter(df['LATITUDE'], df['LONGITUDE'], alpha=0.25)plt.axis('equal')plt.show()

xxxxxxxxxx plt.figure(figsize=(20,10))plt.scatter(range(0, 366), df.loc[df['CRASH TIMESTAMP'].dt.year == 2020].groupby(df['CRASH TIMESTAMP'].dt.date).size().values, label='2020')plt.scatter(range(0, 365), df.loc[df['CRASH TIMESTAMP'].dt.year == 2019].groupby(df['CRASH TIMESTAMP'].dt.date).size().values, label='2019')plt.legend(fontsize=15, loc='lower left')plt.xlabel('Day of Year', fontsize=15)plt.ylabel('Number of Daily Crashes', fontsize=15)plt.show()

xxxxxxxxxx plt.figure(figsize=(20,10))plt.bar((df['CRASH TIMESTAMP'].dt.year).unique(), df.groupby(df['CRASH TIMESTAMP'].dt.year).size())plt.xticks((df['CRASH TIMESTAMP'].dt.year).unique())plt.show()

xxxxxxxxxx

xxxxxxxxxx contributing_factors = np.unique(pd.read_csv('contributing_factors.csv', sep=';')['to'].to_numpy())

xxxxxxxxxx contributing_factors

array(['accelerator defective', 'aggressive driving/road rage',
       'alcohol involvement', 'animals action', 'backing unsafely',
       'brakes defective', 'cell phone', 'driver inattention/distraction',
       'driver inexperience', 'driverless/runaway vehicle', 'drugs',
       'eating or drinking', 'failure to keep right',
       'failure to yield right-of-way', 'fatigued/drowsy', 'fell asleep',
       'following too closely', 'glare', 'headlights defective',
       'illness', 'lane marking improper/inadequate',
       'listening/using headphones', 'lost consciousness',
       'obstruction/debris', 'other electronic device',
       'other lighting defects', 'other vehicular',
       'outside car distraction', 'oversized vehicle',
       'passenger distraction', 'passing or lane usage improper',
       'passing too closely', 'pavement defective', 'pavement slippery',
       'pedestrian/bicyclist/other pedestrian error/confusion',
       'physical disability', 'prescription medication',
       'reaction to other uninvolved vehicle',
       'reaction to uninvolved vehicle', 'shoulders defective/improper',
       'steering failure', 'tinted windows', 'tire failure/inadequate',
       'tow hitch defective',
       'traffic control device improper/non-working',
       'traffic control disregarded', 'turning improperly',
       'unsafe lane changing', 'unsafe speed', 'unspecified',
       'using on board navigation device', 'vehicle vandalism',
       'view obstructed/limited', 'windshield inadequate'], dtype=object)

xxxxxxxxxx i, c = df.groupby('CONTRIBUTING FACTORS').size().index, df.groupby('CONTRIBUTING FACTORS').size().values

xxxxxxxxxx ​

2042

xxxxxxxxxx ​

xxxxxxxxxx

df['ZIP CODE'] = df['ZIP CODE'].astype(str).replace('     ','nan').astype(float)

xxxxxxxxxx

 import numpy as npimport pandas as pdfrom sklearn.neighbors import NearestNeighborsfrom aux import *import time​t1 = time.time()df = pd.read_csv('preprocessed_collisions.csv')t2 = time.time()print(f'Done doing the preprocessing. Time elapsed {t2-t1} seconds.')

Done doing the preprocessing. Time elapsed 8.262746810913086 seconds.

 df['YEAR'] = pd.to_datetime(df['CRASH DATE']).dt.yeardf['MONTH'] = pd.to_datetime(df['CRASH DATE']).dt.month

xxxxxxxxxx

xdf3 = pd.DataFrame({'BOROUGH' : df.groupby('BOROUGH').size().index, 'values' : df.groupby('BOROUGH').size().values})df3['BOROUGH'] = df3['BOROUGH'].apply(lambda x : x.title())​import plotly.express as pxfrom urllib.request import urlopenimport jsonwith urlopen('https://raw.githubusercontent.com/dwillis/nyc-maps/master/boroughs.geojson') as response:    counties = json.load(response)    import plotly.express as px​fig = px.choropleth_mapbox(df3, geojson=counties, locations='BOROUGH', color='values', featureidkey="properties.BoroName",                           color_continuous_scale="Viridis",                           range_color=(0, 500000),                           center={"lat": 40.730610, "lon": -73.935242},                           labels={'values':'Number of crashes'},                           mapbox_style="carto-positron", zoom=9                          )​fig.update_geos(fitbounds="locations", visible=False)fig.update_layout(margin={"r":0,"t":0,"l":0,"b":0})fig.show()

xxxxxxxxxx

ximport plotly.express as pxfrom urllib.request import urlopenimport jsonwith urlopen('https://raw.githubusercontent.com/fedhere/PUI2015_EC/master/mam1612_EC/nyc-zip-code-tabulation-areas-polygons.geojson') as response:    counties = json.load(response)    import plotly.express as px​fig = px.choropleth_mapbox(pd.DataFrame({'ZIP' : df.groupby('ZIP CODE').size().index, 'COUNT' : df.groupby('ZIP CODE').size().values}),                            geojson=counties, locations='ZIP', color='COUNT', featureidkey="properties.postalCode",                           color_continuous_scale="Viridis",                           range_color=(0, 27093),                           center={"lat": 40.730610, "lon": -73.935242},                           labels={'values':'Number of crashes'},                           mapbox_style="carto-positron", zoom=9                          )​fig.update_geos(fitbounds="locations", visible=False)fig.update_layout(margin={"r":0,"t":0,"l":0,"b":0})fig.show()import plotly.express as px

xxxxxxxxxx

ximport plotly.express as pxfig = px.density_mapbox(df.iloc[:100,:], lat='LATITUDE', lon='LONGITUDE', radius=25,                        center=dict(lat=40.730610, lon=-73.935242), zoom=9,                        mapbox_style="carto-positron",                       width = 800, height = 800)fig.show()

xxxxxxxxxx

 df['YEAR'] = pd.to_datetime(df['CRASH DATE']).dt.yeardf['MONTH'] = pd.to_datetime(df['CRASH DATE']).dt.month

xxxxxxxxxx df_test = pd.DataFrame({'BOROUGH' : [x[0].title() for x in df.groupby(['BOROUGH', 'YEAR']).size().index],                        'YEAR' : [x[1] for x in df.groupby(['BOROUGH', 'YEAR']).size().index],                        'COUNT' : df.groupby(['BOROUGH', 'YEAR']).size().values})​#Remove 2012 and 2021.df_test = df_test.loc[df_test['YEAR'].apply(lambda x : x not in [2012, 2021])]​import plotly.express as pxfrom urllib.request import urlopenimport jsonwith urlopen('https://raw.githubusercontent.com/dwillis/nyc-maps/master/boroughs.geojson') as response:    counties = json.load(response)    import plotly.express as px​fig = px.choropleth_mapbox(df_test, geojson=counties, locations='BOROUGH', color='COUNT', featureidkey="properties.BoroName",                           color_continuous_scale="Viridis",                           range_color=(0, 63949),                           animation_frame="YEAR",                           center={"lat": 40.730610, "lon": -73.935242},                           labels={'values':'Number of crashes'},                           mapbox_style="carto-positron", zoom=9,                           width = 800, height = 800                          )​fig.show()from urllib.request import urlopen

xxxxxxxxxx df_test = pd.DataFrame({'ZIP CODE' : [x[0] for x in df.groupby(['ZIP CODE', 'YEAR']).size().index],                        'YEAR' : [x[1] for x in df.groupby(['ZIP CODE', 'YEAR']).size().index],                        'COUNT' : df.groupby(['ZIP CODE', 'YEAR']).size().values})​#Remove 2012 and 2021.df_test = df_test.loc[df_test['YEAR'].apply(lambda x : x not in [2012, 2021])]​df_test = df_test.sort_values(by=['ZIP CODE', 'YEAR'])​import plotly.express as pxfrom urllib.request import urlopenimport jsonwith urlopen('https://raw.githubusercontent.com/fedhere/PUI2015_EC/master/mam1612_EC/nyc-zip-code-tabulation-areas-polygons.geojson') as response:    counties = json.load(response)    import plotly.express as px​fig = px.choropleth_mapbox(df_test, geojson=counties, locations='ZIP CODE', color='COUNT',                            featureidkey="properties.postalCode",                           color_continuous_scale="Viridis",                           range_color=(0, df_test['COUNT'].max()),                           animation_frame="YEAR",                           category_orders={"YEAR": range(2013, 2021)},                           center={"lat": 40.730610, "lon": -73.935242},                           labels={'values':'Number of crashes'},                           mapbox_style="carto-positron", zoom=9,                           width = 800, height = 800                          )​fig.show()

x !pip install jupyter-dash

Collecting jupyter-dash
  Downloading jupyter_dash-0.4.0-py3-none-any.whl (20 kB)
Requirement already satisfied: ipykernel in /opt/anaconda3/lib/python3.7/site-packages (from jupyter-dash) (5.3.4)
Requirement already satisfied: requests in /opt/anaconda3/lib/python3.7/site-packages (from jupyter-dash) (2.25.1)
Requirement already satisfied: ipython in /opt/anaconda3/lib/python3.7/site-packages (from jupyter-dash) (7.20.0)
Requirement already satisfied: flask in /opt/anaconda3/lib/python3.7/site-packages (from jupyter-dash) (1.1.2)
Collecting ansi2html
  Downloading ansi2html-1.6.0-py3-none-any.whl (14 kB)
Requirement already satisfied: dash in /opt/anaconda3/lib/python3.7/site-packages (from jupyter-dash) (1.19.0)
Requirement already satisfied: retrying in /opt/anaconda3/lib/python3.7/site-packages (from jupyter-dash) (1.3.3)
Requirement already satisfied: dash-html-components==1.1.2 in /opt/anaconda3/lib/python3.7/site-packages (from dash->jupyter-dash) (1.1.2)
Requirement already satisfied: future in /opt/anaconda3/lib/python3.7/site-packages (from dash->jupyter-dash) (0.18.2)
Requirement already satisfied: plotly in /opt/anaconda3/lib/python3.7/site-packages (from dash->jupyter-dash) (4.14.3)
Requirement already satisfied: dash-table==4.11.2 in /opt/anaconda3/lib/python3.7/site-packages (from dash->jupyter-dash) (4.11.2)
Requirement already satisfied: dash-core-components==1.15.0 in /opt/anaconda3/lib/python3.7/site-packages (from dash->jupyter-dash) (1.15.0)
Requirement already satisfied: dash-renderer==1.9.0 in /opt/anaconda3/lib/python3.7/site-packages (from dash->jupyter-dash) (1.9.0)
Requirement already satisfied: flask-compress in /opt/anaconda3/lib/python3.7/site-packages (from dash->jupyter-dash) (1.9.0)
Requirement already satisfied: Werkzeug>=0.15 in /opt/anaconda3/lib/python3.7/site-packages (from flask->jupyter-dash) (1.0.1)
Requirement already satisfied: Jinja2>=2.10.1 in /opt/anaconda3/lib/python3.7/site-packages (from flask->jupyter-dash) (2.11.3)
Requirement already satisfied: click>=5.1 in /opt/anaconda3/lib/python3.7/site-packages (from flask->jupyter-dash) (7.1.2)
Requirement already satisfied: itsdangerous>=0.24 in /opt/anaconda3/lib/python3.7/site-packages (from flask->jupyter-dash) (1.1.0)
Requirement already satisfied: MarkupSafe>=0.23 in /opt/anaconda3/lib/python3.7/site-packages (from Jinja2>=2.10.1->flask->jupyter-dash) (1.1.1)
Requirement already satisfied: brotli in /opt/anaconda3/lib/python3.7/site-packages (from flask-compress->dash->jupyter-dash) (1.0.9)
Requirement already satisfied: traitlets>=4.1.0 in /opt/anaconda3/lib/python3.7/site-packages (from ipykernel->jupyter-dash) (5.0.5)
Requirement already satisfied: appnope in /opt/anaconda3/lib/python3.7/site-packages (from ipykernel->jupyter-dash) (0.1.2)
Requirement already satisfied: tornado>=4.2 in /opt/anaconda3/lib/python3.7/site-packages (from ipykernel->jupyter-dash) (6.1)
Requirement already satisfied: jupyter-client in /opt/anaconda3/lib/python3.7/site-packages (from ipykernel->jupyter-dash) (6.1.7)
Requirement already satisfied: pexpect>4.3 in /opt/anaconda3/lib/python3.7/site-packages (from ipython->jupyter-dash) (4.8.0)
Requirement already satisfied: jedi>=0.16 in /opt/anaconda3/lib/python3.7/site-packages (from ipython->jupyter-dash) (0.17.2)
Requirement already satisfied: backcall in /opt/anaconda3/lib/python3.7/site-packages (from ipython->jupyter-dash) (0.2.0)
Requirement already satisfied: pickleshare in /opt/anaconda3/lib/python3.7/site-packages (from ipython->jupyter-dash) (0.7.5)
Requirement already satisfied: decorator in /opt/anaconda3/lib/python3.7/site-packages (from ipython->jupyter-dash) (4.4.2)
Requirement already satisfied: pygments in /opt/anaconda3/lib/python3.7/site-packages (from ipython->jupyter-dash) (2.7.4)
Requirement already satisfied: prompt-toolkit!=3.0.0,!=3.0.1,<3.1.0,>=2.0.0 in /opt/anaconda3/lib/python3.7/site-packages (from ipython->jupyter-dash) (3.0.8)
Requirement already satisfied: setuptools>=18.5 in /opt/anaconda3/lib/python3.7/site-packages (from ipython->jupyter-dash) (52.0.0.post20210125)
Requirement already satisfied: parso<0.8.0,>=0.7.0 in /opt/anaconda3/lib/python3.7/site-packages (from jedi>=0.16->ipython->jupyter-dash) (0.7.0)
Requirement already satisfied: ptyprocess>=0.5 in /opt/anaconda3/lib/python3.7/site-packages (from pexpect>4.3->ipython->jupyter-dash) (0.7.0)
Requirement already satisfied: wcwidth in /opt/anaconda3/lib/python3.7/site-packages (from prompt-toolkit!=3.0.0,!=3.0.1,<3.1.0,>=2.0.0->ipython->jupyter-dash) (0.2.5)
Requirement already satisfied: ipython-genutils in /opt/anaconda3/lib/python3.7/site-packages (from traitlets>=4.1.0->ipykernel->jupyter-dash) (0.2.0)
Requirement already satisfied: python-dateutil>=2.1 in /opt/anaconda3/lib/python3.7/site-packages (from jupyter-client->ipykernel->jupyter-dash) (2.8.1)
Requirement already satisfied: jupyter-core>=4.6.0 in /opt/anaconda3/lib/python3.7/site-packages (from jupyter-client->ipykernel->jupyter-dash) (4.7.1)
Requirement already satisfied: pyzmq>=13 in /opt/anaconda3/lib/python3.7/site-packages (from jupyter-client->ipykernel->jupyter-dash) (20.0.0)
Requirement already satisfied: six>=1.5 in /opt/anaconda3/lib/python3.7/site-packages (from python-dateutil>=2.1->jupyter-client->ipykernel->jupyter-dash) (1.15.0)
Requirement already satisfied: chardet<5,>=3.0.2 in /opt/anaconda3/lib/python3.7/site-packages (from requests->jupyter-dash) (4.0.0)
Requirement already satisfied: urllib3<1.27,>=1.21.1 in /opt/anaconda3/lib/python3.7/site-packages (from requests->jupyter-dash) (1.26.3)
Requirement already satisfied: idna<3,>=2.5 in /opt/anaconda3/lib/python3.7/site-packages (from requests->jupyter-dash) (2.10)
Requirement already satisfied: certifi>=2017.4.17 in /opt/anaconda3/lib/python3.7/site-packages (from requests->jupyter-dash) (2020.12.5)
Installing collected packages: ansi2html, jupyter-dash
Successfully installed ansi2html-1.6.0 jupyter-dash-0.4.0

​

xxxxxxxxxx

df['ZIP CODE'] = df['ZIP CODE'].astype(str).replace('     ','nan').astype(float)

xxxxxxxxxx import plotly.express as pxfrom jupyter_dash import JupyterDashimport dash_core_components as dccimport dash_html_components as htmlfrom dash.dependencies import Input, Output​# Load Datadf = px.data.tips()​# Build Appapp = JupyterDash(__name__)​app.layout = html.Div([    html.H1("JupyterDash Demo"),    dcc.Graph(id='graph'),    html.Label([        "colorscale",        dcc.Dropdown(            id='colorscale-dropdown', clearable=False,            value='plasma', options=[                {'label': c, 'value': c}                for c in px.colors.named_colorscales()            ])    ]),])# Define callback to update graph@app.callback(    Output('graph', 'figure'),    [Input("colorscale-dropdown", "value")])def update_figure(colorscale):    return px.scatter(        df, x="total_bill", y="tip", color="size",        color_continuous_scale=colorscale,        render_mode="webgl", title="Tips"    )# Run app and display result inline in the notebookapp.run_server(mode='inline')

​

	CRASH DATE	CRASH TIME	BOROUGH	ZIP CODE	LATITUDE	LONGITUDE	LOCATION	ON STREET NAME	CROSS STREET NAME	OFF STREET NAME	...	CONTRIBUTING FACTOR VEHICLE 5	COLLISION_ID	VEHICLE TYPE CODE 1	VEHICLE TYPE CODE 2	VEHICLE TYPE CODE 3	VEHICLE TYPE CODE 4	VEHICLE TYPE CODE 5	CONTRIBUTING FACTORS (SPECIFIC)	CONTRIBUTING FACTORS (GENERAL)	VEHICLE TYPES
41	03/12/2021	1:55	BROOKLYN	11226	40.650913	-73.947490	(40.650913, -73.94749)	NaN	NaN	3205 CHURCH AVENUE	...	NaN	4398634	DUMP TRUCK	Sedan	NaN	NaN	NaN	Passing Too Closely	Poor Driving	Car, Truck
55	03/06/2021	16:00	BROOKLYN	11217	40.682010	-73.978360	(40.68201, -73.97836)	NaN	NaN	385 BERGEN STREET	...	NaN	4396634	Sedan	NaN	NaN	NaN	NaN	Passing or Lane Usage Improper	Poor Driving	Car
83	02/23/2021	15:10	MANHATTAN	10025	40.797220	-73.969930	(40.79722, -73.96993)	BROADWAY	NaN	NaN	...	NaN	4394003	Van	NaN	NaN	NaN	NaN	Failure to Yield Right-of-Way	Poor Driving	Van
85	02/22/2021	13:16	BRONX	10472	40.830975	-73.852670	(40.830975, -73.85267)	CROSS BRONX EXPY	NaN	NaN	...	NaN	4395641	PK	Carry All	NaN	NaN	NaN	Following Too Closely	Poor Driving	Car, Truck
86	02/22/2021	5:20	QUEENS	11379	40.712296	-73.889540	(40.712296, -73.88954)	NaN	NaN	67-36 METROPOLITAN AVENUE	...	NaN	4394250	Bus	Station Wagon/Sport Utility Vehicle	NaN	NaN	NaN	Following Too Closely	Poor Driving	Bus, Car
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
1766603	07/01/2012	20:00	STATEN ISLAND	10306	40.552904	-74.136560	(40.5529042, -74.13656)	REDGRAVE AVENUE	DURANT AVENUE	NaN	...	NaN	293146	SPORT UTILITY / STATION WAGON	PASSENGER VEHICLE	NaN	NaN	NaN	Turning Improperly	Poor Driving	Car, Car
1766619	07/01/2012	10:11	MANHATTAN	10002	40.720477	-73.989718	(40.7204773, -73.9897185)	ALLEN STREET	RIVINGTON STREET	NaN	...	NaN	12177	PASSENGER VEHICLE	PASSENGER VEHICLE	NaN	NaN	NaN	Failure to Yield Right-of-Way	Poor Driving	Car, Car
1766623	07/01/2012	16:20	BROOKLYN	11213	40.668785	-73.947817	(40.6687847, -73.9478174)	UNION STREET	NEW YORK AVENUE	NaN	...	NaN	152368	OTHER	PASSENGER VEHICLE	NaN	NaN	NaN	Driver Inexperience	Poor Driving	Car, Other
1766626	07/01/2012	16:49	MANHATTAN	10024	40.791468	-73.974106	(40.7914677, -73.9741062)	BROADWAY	WEST 91 STREET	NaN	...	NaN	57556	UNKNOWN	NaN	NaN	NaN	NaN	Backing Unsafely	Poor Driving	Unknown
1766633	07/01/2012	15:00	QUEENS	11364	40.750591	-73.778117	(40.7505908, -73.7781175)	201 STREET	50 AVENUE	NaN	...	NaN	259355	PASSENGER VEHICLE	PASSENGER VEHICLE	NaN	NaN	NaN	Failure to Yield Right-of-Way	Poor Driving	Car, Car

Kernel Sessions

Terminal Sessions

About the Data (from here)¶

Why does it happen?¶

Where does it happen?¶

When does it happen?¶

Look at the hour for different categories¶

Jitter Plot¶

When do serious / or lethal crashes occur?¶

When in the week do serious accidents occur?¶

Investigation into injury¶

Check the Latitude and Longtitude¶

Which factors mix?¶

Distraction Notebook¶

Introduction Notebook¶

Introduction to the dataset¶

Where do the crashes occur?¶

Where do they occur (zip code?)¶

Heatmap¶

Where do they happen?¶

Poor Driving Notebook¶